Search Results

Indications for Use:
The MAC 7 Resting ECG Analysis System is a non-invasive prescription device.

• The device is indicated for use to acquire, analyze, display and print electrocardiograms.
• The device is indicated for use to provide interpretation of the data for consideration by a physician.
• The device is indicated for use in a clinical setting, by a physician or by trained personnel who are acting on the orders of a licensed physician. It is not intended as a sole means of diagnosis.
• The interpretations of ECG offered by the device are only significant when used in conjunction with a physician over-read as well as consideration of all other relevant patient data.
• The device is indicated for use on adult and pediatric (birth through 21 years of age) populations.

Intended Use:
The MAC 7 Resting ECG Analysis System is intended to acquire, analyze, display, and record electrocardiographic information from adult or pediatric populations. Basic system simultaneously acquires data from each lead. Once the data is acquired, it can be analyzed, reviewed, stored, printed or transmitted. Transmission and reception of ECG data and other clinical data to and from a central clinical information system is optional.

The MAC 7 Resting ECG Analysis System is intended to be used under the direct supervision of a licensed healthcare practitioner, by trained operators in a hospital, medical professional's facility or wherever ECG testing is performed.

The MAC 7 Resting ECG Analysis System is a mobile electrocardiograph designed to acquire, analyze, display, and record ECG signals from surface ECG electrodes.

The device can capture 3, 6, 12 or 15 lead electrocardiograms, provide interpretive analysis, and print reports.

The device can connect to a network, either through a wired LAN connection or via wireless WiFi access points. Once on the network, the device can optionally interface with cardiology information systems such as the GEHC MUSE® system to participate in a complete electrocardiology workflow.

The device provides state-of-the-art information technology security features and a contemporary user interface. Mobility is provided via an optional trolley.

The FDA 510(k) clearance letter for the MAC 7 Resting ECG Analysis System (K251670) does not contain a specific study proving the device meets acceptance criteria. Instead, it establishes substantial equivalence to predicate devices (K203786, K173830, K210560) based on similarities in intended use, indications for use, technology, and performance, along with compliance with voluntary standards and non-clinical testing.

Therefore, the following information is extracted from the provided text to fulfill your request:

1. Acceptance Criteria and Reported Device Performance

The document describes the device's characteristics and compares them to predicate devices, demonstrating substantial equivalence rather than explicit acceptance criteria with numerical performance targets. The "Discussion of Differences" column often highlights that a change does not significantly affect substantial equivalence, implying that the performance remains acceptable.

2. Sample Size Used for the Test Set and Data Provenance

The document states: "Summary of Clinical Tests: The subject of this premarket submission, MAC 7 Resting ECG Analysis System, did not require clinical studies to support substantial equivalence." This indicates that no specific test set data from clinical studies was used for performance evaluation in this submission. The "acceptance" is based on the device's technical characteristics aligning with or improving upon those of legally marketed predicate devices, supported by non-clinical testing and previous clearances for core components (like the 12SL™ analysis algorithm v24).

Therefore, details on sample size, country of origin, or retrospective/prospective nature of a clinical test set are not available in this document.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts

As no clinical studies were required for this submission to support substantial equivalence, there is no information provided regarding experts establishing ground truth for a test set.

4. Adjudication Method for the Test Set

Given that no clinical studies were performed, there is no adjudication method described for a test set.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was Done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

The document does not mention any MRMC comparative effectiveness study. The focus is on establishing substantial equivalence to existing devices, not on demonstrating improved human reader performance with AI assistance.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was Done

The document states that the "Interpretive Statements are provided by 12SL (v24) ECG Analysis Program which was previously cleared under K221321." This implies that the performance of the 12SL™ algorithm itself (a standalone interpretation algorithm) would have been assessed during its prior clearance (K221321). However, the details of that standalone performance study are not included in this K251670 submission.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

Since no new clinical studies were performed for this submission, there is no mention of the type of ground truth used for a test set. For the 12SL™ analysis algorithm (v24) which provides interpretation statements, the ground truth would have been established during its prior clearance (K221321), but those details are not provided here.

8. The Sample Size for the Training Set

The document does not provide information on the sample size for any training set. As noted, the approval is based on substantial equivalence and non-clinical testing rather than specific training data for a new algorithm.

9. How the Ground Truth for the Training Set was Established

The document does not provide information on how ground truth was established for any training set.

Ask a specific question about this device

The AccurECG® Analysis System v2.0 is intended for use by qualified healthcare professionals in the assessment of a patient's recorded ambulatory ECG data. Analysis results are provided in a standard report for review and printing.

The System provides single-lead analysis on a beat-by-beat basis, Ventricular Ectopic Beat and Supraventricular Ectopic Beat detection, heart rate measurement, and rhythm analysis. The AccurECG® Analysis System v2.0 is compatible with ECG recordings taken with silver/silver chloride (Ag / AgCl) electrodes (wet leads).

The AccurECG® Analysis System v2.0 is not for use in life-supporting or sustaining systems or ECG monitor and alarm devices. The System is not intended to be used with cardiac telemetry monitors.

The AccurECG® Analysis System's automated interpretation results are not intended to be the sole means of diagnosis. The AccurECG Report is an adjunct intended to facilitate health care decision making in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information to arrive at a diagnostic conclusion.

The AccurECG® Analysis System v2.0 does not interface with data management systems or hardware and is device independent.

The AccurKardia ECG Analysis System consists of: (1) A client-side web interface which provides tools to upload and review ECG recordings via a web application programming interface (API), and (2) A server-side automated proprietary ECG interpretation support algorithm which measures and analyzes ECGs to provide physicians supportive information for ECG analysis.

AccurECG v2.0 is intended to analyze recordings performed on adults aged 22 and older and works in the following sequence:

i. The web interface allows the user to select files and upload to the AccurECG secure database.

ii. The proprietary AccurECG algorithm analyzes and labels the ECG:

• Delineation – detection of QRS complexes and T waves on the ECG signal through advanced signal processing and image-based techniques.
• Abnormality labels – automated arrhythmia interpretation and statistical classification.

iii. AccurECG® Analysis System v2.0 displays the resulting analysis and original ECG signal with reviewing tools in the web interface.

iv. AccurECG® Analysis System v2.0 allows for preliminary comments summarizing the review before generating a report.

N/A

Ask a specific question about this device

The N10, N12, N15, N10MPro, N12MPro, NM15Pro Multi-parameter Patient Monitors are intended for monitoring, displaying, reviewing, storing, alarming and transferring of multiple physiological parameters including ECG (3-lead, 5-lead, 12-lead selectable), Arrhythmia Analysis, ST Segment Analysis, QT Analysis, Heart Rate (HR) and Heart-Rate-Variability(HRV)), interpretations of resting 12-lead ECG, Respiration rate(Resp), Temperature(Temp), Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP), Pulmonary Artery Wedge Pressure (PAWP), Cardiac Output (C.O.), Carbon Dioxide (CO2). The N10MPro, N12MPro, NM15Pro Multi-parameter Patient Monitors are also intended for monitoring, displaying, reviewing, storing, alarming and transferring of physiological parameters including Masimo Rainbow SpO2, Anesthesia gas (AG), oxygen (O2) respiratory gas monitoring, Bispectral Index (BIS), Respiration Mechanics (RM) and Neuromuscular Transmission Monitoring (NMT). All the parameters can be monitored on single adult, pediatric, and neonatal patient except for the following:

• Arrhythmia analysis is intended to use on adult patients only and is not intended and shall not be used on pediatric and neonatal population.
• NIBP measurement continual mode is not applicable to neonates.
• When using COMEN SpO2, the monitor is intended to be used on adult patient only.
• PAWP is intended for adult and pediatric patients only.
• C.O. measurement is intended for adult patients only.
• BIS monitoring is intended for adult patients only.
• RM is intended for adult and pediatric patients only.
• NMT monitoring is intended for adult and pediatric patients only.

The monitors are to be used in healthcare facilities by healthcare professionals or under their guidance.

The Multi-parameter Patient monitors are not intended for emergency and transport use, aircraft environment or home use.

The monitors are not intend for use as apnea monitors.

The monitors are not intended for use in MRI or CT environments.

The monitors are not used on patients who have a demonstrated need for cardiac monitoring known arrhythmias of VT, Accelerated Idioventricular rhythm and Torsades de Pointes.

There are six (6) models under evaluation, namely N10, N12, N15, N10MPro, N12MPro, N15MPro. All models share the same intended condition of use, the same intended patient population and operator profile, biological safety characteristic and principle of operation. All these models are the same on electric and electrical circuit and components, mechanical construction, software and alarm system. The only difference lies on the screen and configuration of with/without plug-in module slot and the number of battery packs.

N/A

Ask a specific question about this device

DeepRhythmAI is a cloud-based software that utilizes AI algorithms to assess cardiac arrhythmias using a single- or two-lead ECG data from adult patients.

It is intended for use by a healthcare solution integrator to build web, mobile or another types of applications to let qualified healthcare professionals review and confirm the analytic result. The product supports downloading and analyzing data recorded in the compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders when the assessment of the rhythm is necessary.

The product can be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI can be integrated into medical devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

DeepRhythmAI is not for use in life-supporting or sustaining systems or ECG Alarm devices. Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history symptoms and other diagnostic information.

DeepRhythmAI is a cloud-based software utilizing CNN and transformer models for automated analysis of ECG data. It uses a scalable Application Programming Interface (API) to enable easy integration with other medical products. The main component of DeepRhythmAI is an automated proprietary deep-learning algorithm, which measures and analyzes ECG data to provide qualified healthcare professionals with supportive information for review. DeepRhythmAI can be integrated into medical devices. The product supports downloading and analyzing data recorded in compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders used when assessment of the rhythm is necessary.

The DRAI can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI doesn't have User Interface therefore it should be integrated with the external visualization software used by the ECG technicians for ECG visualization and analysis reporting.

DeepRhythmAI is not for use in life supporting or sustaining systems or ECG Alarm devices. Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

DRAI consists of:

1. An API which allows the client to upload single- or two-lead ECG data and allows to download the results of the ECG analysis.
2. The automated proprietary deep-learning algorithm, which measures and analyzes ECG data to provide qualified healthcare professional with supportive information for review.

DRAI works in the following sequence:

1. Accept uploading digital ECG files via secure API;

2. Analyze the uploaded ECG data using a proprietary algorithm, which detects cardiac beats/arrhythmias and intervals including:

   • QRS
   • Heart rate determination
   • RR Interval measurements
   • Non-paced supraventricular rhythm and arrhythmia calls as specified by product's Instruction for Use
   • Non-paced ventricular rhythm and arrhythmia calls: as specified by product's Instruction for Use
   • Atrioventricular blocks (second or third degree)

3. Analyze detected individual Ventricular ectopic beats also known as Premature Ventricular Contractions (PVCs) to form groups and subgroups of similar beat morphology if product is configured to do so.

4. The results of the ECG analysis can be downloaded via secure API by the external visualization software used by healthcare professionals for the ECG visualization and analysis reporting.

This document describes the acceptance criteria and the study proving the device meets these criteria for DeepRhythmAI, a cloud-based software that utilizes AI algorithms to assess cardiac arrhythmias.

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary does not explicitly list quantitative acceptance criteria in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy thresholds). Instead, it states that the device's performance was evaluated against recognized consensus standards and a proprietary database, and that the PVC grouping algorithm meets "predefined requirements for accuracy." Without specific numerical targets, the table below will summarize the types of performance evaluations conducted and the reported outcomes as described.

2. Sample Size for the Test Set and Data Provenance

The 510(k) summary states that "the algorithm was tested against the proprietary database (MDG validation db) that includes a large number of recordings captured among the intended patient population."

• Test Set Sample Size: The exact numerical sample size for the test set is not specified beyond "a large number of recordings."
• Data Provenance:
  • Country of Origin: Not explicitly stated. It refers to a "proprietary database (MDG validation db)."
  • Retrospective or Prospective: Not explicitly stated. Given it's a "validation db," it's likely retrospective data collected over time.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

This information is not provided in the given 510(k) clearance letter. The document mentions "qualified healthcare professionals review and confirm the analytic result" in the context of the device's intended use and that the AI provides "supportive information for review." However, it does not detail how ground truth was established for the validation dataset, nor the number or qualifications of experts involved in that process.

4. Adjudication Method for the Test Set

The adjudication method used for establishing the ground truth for the test set is not provided in the document.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

An MRMC comparative effectiveness study, comparing human readers with AI assistance versus without AI assistance, is not explicitly mentioned or described in the provided 510(k) summary. The device's indication for use states that "Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only," suggesting it functions as an assistive tool, but a formal MRMC study demonstrating improvement is not detailed.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The document states, "the algorithm was tested against the proprietary database (MDG validation db)" and that DeepRhythmAI "measures and analyzes ECG data to provide qualified healthcare professional with supportive information for review." The performance assessment of the "automated proprietary deep-learning algorithm" and the "hierarchical Premature Ventricular Contraction (PVC) clustering algorithm" implies a standalone evaluation of the algorithm's capabilities.

7. Type of Ground Truth Used for the Test Set

The type of ground truth used is not explicitly stated. However, given the nature of ECG analysis for arrhythmias, it is highly probable that the ground truth was established through expert consensus or manual expert annotation of the ECG recordings in the "proprietary database (MDG validation db)."

8. Sample Size for the Training Set

The sample size for the training set is not provided in the document. The document mentions the use of "CNN and transformer models for automated analysis of ECG data," which implies a machine learning approach requiring a training set, but its size is not disclosed.

9. How the Ground Truth for the Training Set Was Established

The method for establishing ground truth for the training set is not provided in the document. As with the test set, it is likely that expert consensus or manual expert annotation was used to label the data for training the deep learning algorithms.

Ask a specific question about this device

Withings BeamO is intended to record, display (when prescribed or used under the care of a physician), store, and transfer single-channel electrocardiogram (ECG) rhythms. It is indicated for use with individuals 22 years and older.

Withings BeamO is a non-sterile, contactless, reusable clinical thermometer intended for the intermittent determination of human body temperature over the temporal artery as the measurement site on people of all ages.

Withings BeamO is also an electronic stethoscope that enables the recording and transmission of auscultation sound data. Withings BeamO is intended to be used by professional users in a clinical environment or by lay users in a non-clinical environment on people of all ages. The electronic stethoscope is for medical diagnostics purposes only. The device is not intended for self-diagnosis.

Withings BeamO, model name SCT02, is a multi-function handheld battery powered device with ECG, stethoscope, temperature capabilities. Withings BeamO can record a 1-lead ECG using two stainless steel electrodes. It analyzes the data collected by the integrated two stainless steel electrodes to generate an one-lead ECG waveform and provides the ECG recording to the user for a given 30 second measurement.

Withings BeamO is also a contactless thermometer that can measure body temperature in adjusted mode.

Withings BeamO is also a digital stethoscope that can be used to auscultate heart and lung sounds. The sensor generates an electric charge when subjected to mechanical vibrations. The charge variations are amplified and digitized by an audio codec. Sound filters are applied to the resulting sound wave in order to listen to the patient's heart and lung sounds with clarity.

Withings BeamO consists of hardware and embedded software. Withings BeamO works in conjunction with a companion software on the Withings App. Withings BeamO communicates with the companion software via Bluetooth Low Energy (BLE). The device measurement results and recordings are synchronized with the companion software using Wi-Fi/Cellular data via the Withings servers.

Withings BeamO does not include ECG analysis or ECG-derived heart rate functionalities.

N/A

Ask a specific question about this device

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for providing Non-Stress testing or fetal monitoring for pregnant women from the 28th week of gestation. It is intended to be used only by trained and qualified personnel in antepartum examination rooms, labor and delivery rooms.

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for real time monitoring of fetal and maternal physiological parameters, including non-invasive monitoring and invasive monitoring:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The F15A series fetal and maternal monitor can monitor multiple physiological parameters of the fetus/mother in real time. F15A series can display, store, and print patient information and parameters, provide alarms of fetal and maternal parameters, and transmit patient data and parameters to Central Monitoring System.

F15A series fetal and maternal monitors mainly provide following primary feature:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The provided FDA 510(k) clearance letter and summary for the Fetal & Maternal Monitor (F15A, F15A Air) do not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and the study that proves the device meets them.

The document focuses primarily on demonstrating substantial equivalence to a predicate device (Edan Instruments, Inc., F9 Express Fetal & Maternal Monitor, K173042) through comparison of intended use, technological characteristics, and conformance to various safety and performance standards. It mentions "functional and system level testing to validate the performance of the devices" and "results of the bench testing show that the subject device meets relevant consensus standards," but it does not specify quantitative acceptance criteria for each individual physiological parameter (e.g., FHR accuracy, SpO2 accuracy) nor the specific results of those tests beyond stating that they comply with standards.

Specifically, the document does not include information on:

• A table of acceptance criteria with specific quantitative targets for each parameter and the reported device performance values against those targets. It only states compliance with standards.
• Sample sizes used for a "test set" in the context of clinical performance evaluation (it mentions "bench testing," but this is typically laboratory-based and doesn't involve patient data in a "test set" sense for AI/algorithm performance validation).
• Data provenance for such a test set (e.g., country of origin, retrospective/prospective).
• Number or qualifications of experts used to establish ground truth.
• Adjudication methods.
• Multi-Reader Multi-Case (MRMC) studies or human reader improvement data with AI assistance.
• Standalone (algorithm-only) performance, as this is a monitoring device, not a diagnostic AI algorithm.
• Type of ground truth (beyond "bench testing" which implies engineered signals or controlled environments).
• Sample size for a training set or how ground truth for a training set was established. This device is a traditional medical device, not an AI/ML-driven diagnostic or interpretative algorithm in the way your request implies.

Therefore, based solely on the provided text, I can only address what is present or infer what is missing.

Here's a breakdown based on the available information:

Analysis of Acceptance Criteria and Performance Testing based on Provided Document

The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (F9 Express Fetal & Maternal Monitor, K173042) by showing that the new device (F15A, F15A Air) has the same intended use and fundamentally similar technological characteristics, with any differences not raising new safety or effectiveness concerns.

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table with quantitative acceptance criteria for each physiological parameter (e.g., FHR accuracy, SpO2 accuracy) and the corresponding reported performance values obtained in testing. Instead, it states that the device was assessed for conformity with relevant consensus standards. For example, it lists:

• IEC 60601-2-37:2015: Particular requirements for the basic safety and essential performance of ultrasonic medical diagnostic and monitoring equipment (relevant for FHR).
• ISO 80601-2-61:2017+A1:2018: Particular requirements for basic safety and essential performance of pulse oximeter equipment (relevant for SpO2).
• ISO 80601-2-56:2017+A1:2018: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement (relevant for TEMP).
• IEC 60601-2-27:2011: Particular requirements for the basic safety and essential performance of electrocardiographic monitoring equipment (relevant for MECG/DECG).

Acceptance Criteria (Inferred from standards compliance): The acceptance criteria are implicitly the performance requirements specified within these listed consensus standards. These standards set limits for accuracy, precision, response time, and other performance metrics for each type of measurement.

Reported Device Performance: The document states: "The results of the bench testing show that the subject device meets relevant consensus standards." This implies that the measured performance statistics (e.g., accuracy, bias, precision) for each parameter fell within the acceptable limits defined by the respective standards. However, the specific measured values are not provided in this summary.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document mentions "Bench Testing" which implies laboratory-based testing using simulators, controlled signals, or phantoms, rather than a "test set" involving patient data. There is no information provided regarding:

• Sample size (e.g., number of recordings, duration of recordings, number of simulated cases) for the bench tests for each parameter.
• Data provenance (e.g., country of origin, retrospective or prospective) as this is not a study involving patient data collection for performance validation.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This is not applicable and not provided. For a traditional physiological monitor, ground truth for bench testing is typically established using:

• Calibrated reference equipment/simulators: e.g., ECG simulators to generate known heart rates, SpO2 simulators to generate known oxygen saturation levels.
• Physical standards/phantoms: e.g., temperature baths at known temperatures.
• Known physical properties: e.g., precise weights for pressure transducers.

Clinical experts are not involved in establishing ground truth for bench performance of these types of physiological measurements.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This is not applicable and not provided. Adjudication methods are relevant for human expert review of complex clinical data (e.g., medical images for AI validation) to establish a consensus ground truth. For bench testing of physiological monitors, ground truth is objectively determined by calibrated instruments or defined physical parameters.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

This is not applicable and not provided. An MRMC study is typically performed to evaluate the diagnostic accuracy of AI-assisted human interpretations versus unassisted human interpretations for AI-driven diagnostic devices. The Fetal & Maternal Monitor is a physiological monitoring device, not an AI-assisted diagnostic imaging or interpretation system. It measures and displays physiological parameters; it does not provide AI-driven assistance for human "readers" to interpret complex clinical information.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The device is a monitor that directly measures physiological parameters. It is not an "algorithm only" device in the sense of an AI model providing a diagnostic output. Its performance (e.g., FHR accuracy) is its standalone performance, as it directly measures these parameters. The document states "functional and system level testing to validate the performance of the devices," which would represent this type of standalone performance for the measurement functionalities. However, specific quantitative results are not given, only compliance with standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

As explained in point 3, the ground truth for bench testing of physiological monitors is established using calibrated reference equipment/simulators and physical standards.

8. The sample size for the training set

This is not applicable and not provided. This device is a traditional physiological monitor, not a machine learning model that requires a "training set." Its algorithms for parameter measurement are based on established physiological principles and signal processing techniques, not on statistical learning from large datasets.

9. How the ground truth for the training set was established

This is not applicable and not provided for the same reasons as point 8.

Ask a specific question about this device

The Cardiologs Holter Platform is intended for use by qualified healthcare professionals for the assessment of arrhythmias using ECG data in the adult and pediatric population.

The product supports downloading and analyzing data recorded in compatible formats from any device used for the arrhythmia diagnostics such as Holter, event recorder, 12 lead ambulatory ECG devices, or other similar devices indicated for recording heart rhythm.

The Cardiologs Holter Platform can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system.

The Cardiologs Holter Platform provides ECG signal processing and analysis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, interval measurement, heart rate measurement and rhythm analysis. The Cardiologs Holter Platform is not for use in life supporting or sustaining systems or ECG monitor and physiological alarm devices.

The product can be integrated into computerized ECG monitoring devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

Cardiologs Holter Platform interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns patient background, clinical history, symptoms, and other diagnostic information.

Cardiologs Holter Platform is comprised of:

• An interface, which provides tools to measure, analyze and review numerous ECGs;
• An automated proprietary ECG interpretation support algorithm using artificial intelligence (AI) to analyze ECGs to provide clinicians with supportive information for ECG diagnosis.

Cardiologs Holter Platform is an online portal that can be accessed through a network connection and allows the clinician to review and annotate the ECG signals. Alternatively, the Cardiologs Holter Platform can be accessed via an Application Programming Interface (API) connection. The API connection allows a digital ECG upload from a connected device and allows the connected device to receive the output of the Cardiologs ECG interpretation support algorithm and further process and display its output in their system.

Cardiologs Holter Platform is intended to analyze recordings from devices used for the arrhythmia diagnostics such as Holter, event recorder, 12 lead ambulatory ECG devices, or other similar devices for the assessment of heart rhythm in adult and pediatric populations.

Cardiologs Holter Platform works in the following way:

1. Upload of a digital ECG file to Cardiologs' secure hosting databases;

   • i. Manual upload: via the web-interface
   • ii. Direct upload: no manual intervention required, upload occurs whenever the third-party hardware or software system is connected to the Cardiologs' Application Programming Interface (or API) and the ECG is automatically sent to the Cardiologs' servers.

2. Processing of the uploaded ECG file;

3. Analysis and annotation of the uploaded ECG performed by Cardiologs' proprietary algorithm;

4. Display the analysis of the ECG, along with the original signal, to the clinician for review of patient data. The algorithm output may be accessed/displayed through the following interfaces:

   • i. The clinician can access the algorithm output directly within Cardiologs using Cardiologs' user interface.
   • ii. The clinician can access the algorithm output in their own downstream system. The downstream system receives the output of the algorithm via Cardiologs' Application Programming Interface (API).
   • The Cardiologs Holter Platform allows for editing and/or validation of the measurements and parameters by the analyzing clinician.

5. A PDF report is generated as the result of the analysis.

The provided FDA 510(k) clearance letter for the Cardiologs Holter Platform (K250569) does not contain the detailed information required to describe the acceptance criteria and the specific study proving the device meets these criteria.

The letter states:

• "Performance testing demonstrates that the proposed device is as safe and effective and performs as well as the predicate." (Page 6 & 7)
• "No clinical testing was performed in support of this premarket notification." (Page 7)
• "The modified device includes performance updates to enhance the accuracy of the currently cleared abnormalities and measurements and expanded pediatric indications." (Page 6)

This indicates that internal performance testing was conducted, likely against the predicate device's performance, but the details of these tests (acceptance criteria, performance results, sample sizes, ground truth establishment, etc.) are not included in this public facing letter. Such information would typically be found in the full 510(k) submission document, which is not provided here.

Therefore, I cannot fulfill your request with the given input. The document is a clearance letter, which summarizes the outcome of the FDA's review, but does not detail the technical studies and their results.

Ask a specific question about this device

The monitors are intended to be used for monitoring, storing, recording, and reviewing of, and to generate alarms for, multiple physiological parameters of adults and pediatrics (including neonates). The monitors are intended for use by trained healthcare professionals in hospital environments.

The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), functional oxygen saturation of arterial hemoglobin (SpO₂), pulse rate (PR), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), carbon dioxide (CO2), and cardiac output (C.O.).

The arrhythmia detection and ST Segment analysis are intended for adult patients.

The NIBP monitoring supports iCUFS algorithm and iFAST algorithm. The iCUFS algorithm is intended for adult, pediatric and neonatal patients. The iFAST algorithm is intended for adult and pediatric patients (≥3 years of age). Both measurement algorithms are also intended for use with pregnant women, including pre-eclamptic patients. NIBP MAP is not applicable to pregnant women.

The Spot Temp with T2A module can only measure temperature of adult and pediatric (> 1 year of age) patients.

The monitors are not intended for MRI environments.

The cardiac output (C.O.) is only intended for adult patients.

The CX&UX series Patient Monitor including CX10/CX12/CX15/UX10/UX12/UX15 can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormalities so that doctors and nurses can respond to the patient's situation as appropriate.

Minor differences from the predicate device are limited to some modifications of monitoring parameter specifications. These updates do not change the fundamental scientific technology of the cleared predicate device and thus do not raise any questions about the safety and effectiveness of the subject device.

The provided FDA 510(k) clearance letter details the device's technical specifications and comparisons to predicate devices, along with the non-clinical performance data and adherence to various IEC and ISO standards. However, it explicitly states: "Clinical data: The subject device did not require new clinical studies to support substantial equivalence."

This means that the submission for this Patient Monitor device (CX10, CX12, CX15, UX10, UX12, UX15) relies on demonstrating substantial equivalence to a legally marketed predicate device (Edan Instruments, Inc., Patient Monitor Model iX10, iX12, iX15, K232962) through non-clinical performance testing and software verification/validation, rather than new clinical trials or studies involving human patients.

Therefore, the requested information regarding acceptance criteria and studies that prove the device meets acceptance criteria through clinical performance (e.g., sample size for test set, expert involvement, MRMC studies, ground truth establishment for test/training sets, effect size of human reader improvement with AI) cannot be extracted from this document, as such clinical studies were explicitly not required for this 510(k) submission.

The document focuses on demonstrating that the new device's technical specifications and performance are similar to the predicate device, and that it complies with relevant safety and performance standards through bench testing.

Here's what can be extracted from the provided text regarding acceptance criteria and the type of study performed, specifically focusing on the non-clinical aspects:

Device: Patient Monitor (CX10, CX12, CX15, UX10, UX12, UX15)

The acceptance criteria for this device are implicitly tied to its performance meeting the standards and accuracy specifications of the predicate device and relevant international standards. Since no new clinical studies were conducted, the "proof" comes from non-clinical bench testing and software validation.

1. Table of Acceptance Criteria and Reported Device Performance (Non-Clinical/Bench Testing)

2. Sample Size Used for the Test Set and Data Provenance:

• Sample Size: Not applicable in terms of human subjects or patient data test sets, as "new clinical studies" were not required. The "test set" refers to bench testing and functional system-level validation. The specific number of test cycles or a detailed breakdown of test cases for bench testing is not provided in this summary.
• Data Provenance: The data primarily originates from Edan Instruments Inc. (Shenzhen, Guangdong, China) through internal engineering and quality assurance processes for non-clinical bench testing and software validation. It is not patient data, so concepts like "retrospective or prospective" do not apply.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

• Not applicable for clinical ground truth: Since no clinical studies were performed requiring human interpretation or diagnosis for a test set, no medical experts (e.g., radiologists) were used to establish ground truth in this context.
• Internal experts: Bench testing and software validation would have involved engineers and quality assurance professionals, whose qualifications are implicit in the quality system (21 CFR Part 820) but not specified in detail here.

4. Adjudication Method for the Test Set:

• Not applicable: Adjudication methods (e.g., 2+1, 3+1) are relevant for clinical studies involving multiple readers. This was not a clinical study. Bench testing relies on established technical specifications and standard compliance.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:

• No: No MRMC study was performed as no new clinical studies were required or conducted. Therefore, there's no effect size of human readers improving with AI assistance. The device is a patient monitor, not an AI-assisted diagnostic tool.

6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was Done:

• Yes (for the technical components): The "performance testing-Bench" effectively represents a standalone evaluation of the device's functional components (ECG, NIBP, SpO2, etc.) and software against defined technical specifications and standards. The "software verification and validation testing" also represents a standalone evaluation of the algorithm and software functions. The specific algorithms (e.g., iCUFS, iFAST for NIBP, arrhythmia analysis logic) are tested independently for their accuracy against known inputs or reference standards as part of bench testing.

7. The Type of Ground Truth Used:

• Technical/Reference Standards: For the bench testing, the "ground truth" would be derived from:
  • Reference standards/simulators: Calibrated medical equipment, physiological simulators, and test signals (e.g., known ECG waveforms, simulated blood pressure readings, temperature standards) are used to provide the "true" values against which the device's measurements are compared.
  • Defined specifications: The device's internal design specifications and the requirements of the referenced IEC/ISO standards serve as the "ground truth" for compliance testing.
• Not clinical ground truth: No expert consensus, pathology, or outcomes data from real patients were used for establishing ground truth for this submission.

8. The Sample Size for the Training Set:

• Not applicable: The device is a patient monitor, not a machine learning/AI algorithm that typically undergoes a distinct "training" phase with a large dataset. Its functionality is based on established physiological measurement principles and programmed algorithms. Any internal calibration or algorithm refinement would be part of the product development process, not a dedicated "training set" in the AI/ML sense.

9. How the Ground Truth for the Training Set Was Established:

• Not applicable: As there was no "training set" in the context of an AI/ML model, the concept of establishing ground truth for it does not apply to this 510(k) submission.

In summary, this 510(k) clearance relies on demonstrating that the new Patient Monitor is substantially equivalent to a previously cleared predicate device, primarily through robust non-clinical bench testing and software validation, proving compliance with established medical device standards and functional specifications. No new clinical studies with patient data were required or conducted for this specific submission.

Ask a specific question about this device

ZBPro Diagnostic is a cloud-based medical device intended for use by qualified healthcare professionals in the detection and analysis of common cardiac arrhythmias in Holter ECG data in the adult, non-paced population.

The product supports downloading and analyzing Lead II, CM5 (Ch 1), or Modified-MLII (Ch 2+) on retrospective 3-lead and 5-lead 24/48-hour Holter ECG recordings collected using standard Ag/AgCl wet electrodes in adult, non-paced patients. ZBPro is not intended for use with multi-lead analysis, wearable patches, or pediatric/paced recordings.

ZBPro Diagnostic can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system.

ZBPro Diagnostic provides ECG signal processing and analysis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, R-R interval measurement, heart rate measurement, and rhythm analysis.

ZBPro Diagnostic is not for use in life-supporting or sustaining systems or ECG monitor and Alarm devices.

The product can be integrated into computerized ECG monitoring devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

ZBPro Diagnostic interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

ZBPro is cloud-based Software as a Medical Device which aids healthcare professionals in interpreting ambulatory ECG recordings. The software comprises a secure web interface and a backend server hosted on Amazon Web Server (AWS). Authenticated users upload compatible 24-48 hour Holter ECG recordings via a web browser through an Application Programming Interface (API). ZBPro's proprietary ECG interpretation algorithm analyzes and annotates ECGs to provide supportive information for ECG and arrhythmia analysis.

ZBPro provides beat-by-beat ECG signal processing and analysis, QRS detection, Ventricular Ectopic Beat detection, R-R interval measurement, heart rate and Heart Rate Variability measurement, and rhythm analysis.

ZBPro consists of:

1. A web interface which provides tools to upload data, measure, analyze and review numerous ECGs and patient diary logs, make manual annotation and generate ECG reports.
2. An automated proprietary ECG interpretation algorithm which measures and analyzes ECGs to provide adjunct information for ECG diagnosis.

The backend application is established in Amazon Web Services (AWS) and accessed through an Internet connection and a web browser to perform ECG analysis and generate reports.

The provided FDA 510(k) clearance letter and summary for ZBPro Diagnostic contains information related to the device's acceptance criteria and the study conducted to prove it meets them. However, it does not provide explicit details for all the requested points, particularly numerical metrics for acceptance criteria and specific performance results. Instead, it refers to compliance with standards and successful completion of validation.

Here's an extraction of the available information, with notes on what is not explicitly stated:

Acceptance Criteria and Reported Device Performance

The document states that "All clinical input requirements were validated against a gold standard," and "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database in accordance with ANSI/AAMI EC57 and IEC 60601-2-47 reporting conventions." This implies the acceptance criteria were defined by these standards. However, the exact numerical thresholds for sensitivity, specificity, accuracy, etc., for each specific arrhythmia or beat type, are not explicitly stated in the provided text. Similarly, the reported numerical device performance (e.g., specific percentages for sensitivity or specificity) is also not given.

The table below reflects what can be inferred or is directly mentioned regarding the device's performance against its expected functions, without specific quantitative results.

Study Details:

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: The document mentions "an adjudicated database" for performance validation testing but does not specify the sample size (number of patients or recordings) used for this test set.
   • Data Provenance: The document does not specify the country of origin of the data. It states the testing was done on "retrospective 3-lead and 5-lead 24/48-hour Holter ECG recordings." This confirms the data was retrospective.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The document states "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database." This implies that experts were involved in adjudication to establish ground truth. However, the number of experts used and their specific qualifications (e.g., radiologist with X years of experience) are not explicitly stated.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • The term "adjudicated database" is used, indicating that a formal process was followed to establish ground truth. However, the specific adjudication method (e.g., 2+1, 3+1) is not explicitly described in the provided text.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study involving human readers with and without AI assistance is mentioned. The study described focuses on the standalone performance of the algorithm against an adjudicated ground truth and user interface usability.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Yes, a standalone performance evaluation of the algorithm was conducted. The document states: "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database." This refers to the algorithm's performance independent of a human-in-the-loop scenario.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The ground truth was established through expert consensus/adjudication, as indicated by the phrase "adjudicated database."

7. The sample size for the training set:

   • The document does not provide any information regarding the sample size of the training set used for the ZBPro Diagnostic algorithm.

8. How the ground truth for the training set was established:

   • The document does not provide any information on how the ground truth for the training set was established. It only refers to the "adjudicated database" for performance validation testing (typically the test set).

Ask a specific question about this device

The TeleRehab® Aermos Cardiopulmonary Rehabilitation System is intended to acquire and condition the ECG signal from a patient so that it can be transmitted wirelessly from a radiofrequency transmitter to a workstation in a hospital or a clinical setting where the data is displayed and analyzed. This device also measures heart rate and provides visual and audible alarms if the patient's heart rate goes out of a prescribed range. This device is for use with ambulatory adult patients who need monitoring while undergoing cardiovascular and/or pulmonary rehabilitation. The physiological data from monitoring and other patient information (such as patient demographics, exercise protocol and medical information) is stored in a database for tracking and reporting of the patients' progress through rehabilitation.

The TeleRehab® Aermos Cardiopulmonary Rehabilitation System ("Aermos") provides the ECG monitoring functionality required for performing rehabilitation of cardiovascular and/or pulmonary patients. Patients' ECG may be monitored using the Aermos system during exercise under clinical supervision. During monitoring, Aermos provides both visual and audible alarms if the patient's heart rate goes out of a prescribed range. The heart rate alarm indication is one of multiple inputs a clinician may use to modify and adjust rehabilitation activities such as decreasing the patient's level of physical exertion or halting the exercise entirely.

Aermos also provides the ability to plan a patient's rehabilitation program and document the patient's progress through the creation of various types of reports. The report types supported in Aermos include individual treatment plan reports, daily exercise session reports and various patient information reports. Additionally, the Aermos system provides the ability to transfer various report types to the hospital Electronic Medical Records system.

The main components of Aermos are Argus ECG transmitters, the Aermos Workstation and associated networking equipment.

This FDA 510(k) clearance letter pertains to the TeleRehab Aermos Cardiopulmonary Rehabilitation System, which is a device for monitoring ECG signals and heart rate during patient rehabilitation. The provided documentation (the 510(k) Summary) details non-clinical bench testing for performance and safety but explicitly states that clinical testing was not applicable.

Therefore, based on the provided document, the following information regarding acceptance criteria and a study that proves the device meets those criteria, specifically concerning an AI/algorithm-driven component with clinical performance metrics, cannot be fully extracted or is explicitly stated as not performed:

Here's an analysis of the provided information relative to your request:

Acceptance Criteria and Device Performance (Based on Non-Clinical Bench Testing)

Since no clinical study was performed, the "reported device performance" would pertain to the results of non-clinical bench testing against established performance standards. The document does not provide specific quantitative acceptance criteria or reported numerical performance results for the device. Instead, it states that the device's specifications were "verified through internal verification testing" and its usability "evaluated through internal validation testing," and that it complies with various international standards.

Study Details (Based on the provided 510(k) Summary)

1. A table of acceptance criteria and the reported device performance:

   • See the table above. Specific quantitative acceptance criteria beyond "compliance with standard" are not provided in this regulatory summary.

2. Sample size used for the test set and the data provenance:

   • The document explicitly states "Clinical Testing: Not applicable."
   • For the non-clinical bench testing, specific sample sizes (e.g., number of devices tested, number of test cases) are not detailed in this 510(k) summary.
   • Data provenance for non-clinical testing would typically be internal laboratory data generated during device development and verification. There is no mention of geographical origin or retrospective/prospective nature as this was not clinical data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not applicable, as no clinical study with human interpretation/ground truth was performed. The "ground truth" for bench testing would be defined by validated test equipment and reference standards.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not applicable, as there was no study involving human readers or interpretation requiring adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, if so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC study was done, as clinical testing was "Not applicable." The device is a physiological signal monitor, not an AI-assisted diagnostic tool that interprets images or signals requiring human reader comparison.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • The core functionality of the device (ECG acquisition, heart rate measurement, alarms) is algorithmic. The performance of these algorithms would have been assessed during the non-clinical bench testing, which is essentially "standalone algorithm" testing against known inputs and expected outputs. Specific quantitative results (e.g., algorithm accuracy for heart rate) are not provided in this summary beyond "compliance with IEC 60601-2-27" and "ANSI/AAMI EC57: 2012, Testing and Reporting Performance Results of Cardiac Rhythm and ST-Segment Measure Algorithms."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • For non-clinical bench testing, the "ground truth" is typically established by:
     • Reference standards and calibrated test equipment: For electrical performance, signal acquisition accuracy, frequency response, etc.
     • Simulated physiological signals: For testing heart rate calculation and alarm thresholds.
     • Design specifications and established engineering principles: For software functionality and cybersecurity.

8. The sample size for the training set:

   • Not applicable. The device is a monitoring system and not primarily driven by a deep learning or machine learning algorithm that requires a "training set" in the sense of a large dataset for model development. The algorithms for heart rate calculation, etc., are likely traditional signal processing algorithms.

9. How the ground truth for the training set was established:

   • Not applicable, as there was no training set for a machine learning model.

Summary of Device Nature and Regulatory Pathway:

The TeleRehab Aermos Cardiopulmonary Rehabilitation System is a Class II device (Product Codes DRG, DRT) which functions as a physiological signal transmitter and receiver. It monitors ECG and heart rate and provides alarms. Its 510(k) clearance relied on demonstrating substantial equivalence to predicate devices primarily through non-clinical bench testing against recognized industry standards (e.g., IEC 60601 series, ANSI/AAMI, ISO standards) and adherence to FDA guidance documents (e.g., for software, cybersecurity, reprocessing). The explicit statement "Clinical Testing: Not applicable" indicates that the nature of the device and its intended use, combined with the comprehensive non-clinical data, satisfied the FDA's requirements for demonstrating safety and effectiveness without the need for a human-subject clinical study. This is common for devices that are evolutionary improvements on existing technologies with well-understood performance parameters.

Ask a specific question about this device